Files, embeddings, and RAG with Google

2. The File API. For files too big to inline, or that you reuse across many requests, upload once and reference the handle. Still long-context retrieval, just managed better.

3. Embeddings + a vector store (true RAG). When you have hundreds of documents, or need to retrieve across a corpus that exceeds the context windowcontext windowThe context window is the maximum amount of text (measured in tokens) a language model can process at once, including both the input prompt and the generated output.Voir la définition complète →, you embed chunks, store the vectors, and retrieve the relevant ones per query.

The instinct from the foundations block is to jump to RAG. Resist it. If the whole corpus fits in context, long context beats RAG on accuracy and simplicity. ReachReachThe number of unique people exposed to your message in a given period. Unlike impressions, reach counts each person once, no matter how often they see it.Voir la définition complète → for embeddings when scale or cost forces you to.

Strategy 1: Just upload the file

In Google AI Studio, drag your handbook PDF into a prompt and ask. Native multimodality means Gemini reads the PDF directly, including tables and layout, no OCR step.

For the APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète →, small files can be sent inline as bytes. But the moment a file is large, or you will ask many questions against it, use the File APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète → instead.

Strategy 2: The File APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète → for large, reusable files

The File API stores a file on Google's side and gives you a handle. You upload once, then reference it across many requests without re-sending bytes each time. Uploaded files are retained for a limited period (currently around 48 hours) and are free to store, which makes this ideal for a "load the handbook, ask ten questions" session.

That is the whole "answer from our handbook" flow for a single document. Flash is the right tier here: fast, cheap, and more than capable of reading one PDF. Save Pro for harder reasoning over messy, multi-document inputs.

The official guide for upload limits and supported types lives at ai.google.dev. Check it rather than guessing at size caps, which change.

When long context stops being enough

Long context is wonderful until it isn't. Three signals tell you to move to real RAG:

• The corpus exceeds the window. Fifty handbooks, a wiki export, years of policy memos. You cannot inline all of it.
• Cost per query matters. You pay for input tokenstokensA token is the basic unit of text that language models process, often a word fragment, whole word, or punctuation mark rather than a single character.Voir la définition complète →. Sending the entire handbook on every one of 10,000 daily questions is wasteful when each answer needs two paragraphs.
• You need precise, citable provenance across many sources, not "somewhere in this big blob."

This is where embeddings earn their place.

Strategy 3: embeddings and true RAG

You already know the RAG concept. Here is how it maps to Google's specific tools.

An embeddingembeddingAn embedding is a numerical vector that represents data (text, images, or items) in a way that captures meaning, so similar items sit close together in space.Voir la définition complète → is a vector (a list of numbers) that captures the meaning of a chunk of text, so that semantically similar chunks sit near each other in vector space. You embed your document chunks once, store the vectors, embed the user's question at query time, and retrieve the nearest chunks to feed into Gemini.

Google's current embeddingembeddingAn embedding is a numerical vector that represents data (text, images, or items) in a way that captures meaning, so similar items sit close together in space.Voir la définition complète → model is gemini-embedding-001, available through the same Gemini APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète →. One important detail: it supports a task type parameter. You tell it whether you are embeddingembeddingAn embedding is a numerical vector that represents data (text, images, or items) in a way that captures meaning, so similar items sit close together in space.Voir la définition complète → a document for storage (RETRIEVAL_DOCUMENT) or a query for searching (RETRIEVAL_QUERY). Setting this correctly meaningfully improves retrieval quality, and skipping it is the most common mistake.

Step 1: Chunk and embed your documents

Split the handbook into sections (by heading is ideal), then embed each chunk as a document.

In production you store these vectors in a vector databasevector databaseA vector database stores data as high-dimensional numeric vectors (embeddings) and retrieves items by similarity rather than exact matches, powering semantic search and AI applications.Voir la définition complète →. For a small internal tool, an in-memory list with cosine similarity is genuinely fine. For scale, Vertex AI offers a managed option (more on that below).

Step 2: Embed the query and retrieve

Note the task_type difference: documents were embedded as RETRIEVAL_DOCUMENT, the question as RETRIEVAL_QUERY. Same model, asymmetric roles.

Step 3: Generate a grounded answer

Now feed only the retrieved chunks into Gemini. This is the payoff: a tiny, cheap prompt instead of the whole handbook.

That "answer using ONLY the excerpts, and say so if absent" instruction is your guardrail against hallucinationhallucinationA hallucination is when an AI model generates output that is fluent and confident but factually wrong, fabricated, or unsupported by its source data.Voir la définition complète →. RAG does not stop a model from inventing answers; the prompt discipline does.

Don't confuse RAG with grounding with Google Search

A frequent mix-up: grounding with Google Search is not RAG over your private documents. It connects Gemini to the live public web, so the model can answer questions about current events with citations. Your handbook is private and not on the public web, so Search grounding will not help with it. You enable Search grounding as a tool in the APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète →; you build the embeddings pipelinepipelineAll active sales opportunities across the stages of the sales process, together with their combined potential value and probability of closing.Voir la définition complète → above for your own files. Use both when a query needs public facts *and* internal policy.

Scaling up: vertex AI and managed RAG

Everything above runs on the Gemini APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète → and is perfect for prototypes and internal tools. When you need enterprise controls (data residency, IAM, scale, audit logging), move to Vertex AI, Google Cloud's managed AI platform.

Vertex offers RAG Engine, a managed pipelinepipelineAll active sales opportunities across the stages of the sales process, together with their combined potential value and probability of closing.Voir la définition complète → that handles chunking, embeddingembeddingAn embedding is a numerical vector that represents data (text, images, or items) in a way that captures meaning, so similar items sit close together in space.Voir la définition complète →, vector storage, and retrieval for you. You point it at a corpus in Cloud Storage or Drive, and it returns grounded responses. You write far less plumbing, and you get the governance that a security team will ask about. Start at cloud.google.com/vertex-ai.

Rough rule of thumb:

• Prototype or personal tool: Gemini APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète → + your own vector storevector storeA vector database stores data as high-dimensional numeric vectors (embeddings) and retrieves items by similarity rather than exact matches, powering semantic search and AI applications.Voir la définition complète → (the code above).
• Production with compliance needs: Vertex AI RAG Engine.
• Agentic retrieval inside a larger workflow: wrap retrieval as a tool in the Agent Development Kit (ADK) so an agent can decide when to search the handbook versus the web.

The no-code path: where your handbook already lives

Not every "answer from our handbook" problem needs a pipelinepipelineAll active sales opportunities across the stages of the sales process, together with their combined potential value and probability of closing.Voir la définition complète →. If your handbook is a Google Doc in a shared Drive, you have lighter options:

• A Gem (a custom, reusable Gemini configuration) can be given the handbook as reference and a fixed instruction like "answer HR questions citing the policy section." Non-technical colleagues get a tuned assistant with zero code. See support.google.com for setup.
• Gemini in Google Workspace can reason over files in Drive and answer in Docs or Gmail directly, using the "@" file referencing in the side panel.
• For something more custom but still no infrastructure, Apps Script lets you call the Gemini APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète → from inside Workspace, for example a Sheet that classifies support tickets against handbook categories.

The lesson: match the tool to the user and the scale. A Gem may solve in five minutes what you were about to spend a week coding.

A practical decision flow

When someone says "make our handbook answerable," ask:

1. One document, occasional use? Upload it. File APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète →. Done.

2. A few docs, technical owner, prototype? Embeddings + in-memory similarity (the code above).

3. Many docs, production, compliance? Vertex AI RAG Engine.

4. Non-technical owner, doc in Drive? A Gem or Workspace side panel.

5. Needs public web facts too? Add grounding with Google Search.

Key Takeaways

• Try long context before RAG. If the corpus fits the window, the File APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.Voir la définition complète → gives more accurate answers with far less code. Only build embeddings when scale, cost, or provenance forces you to.
• Set `task_type` on every embedding call: RETRIEVAL_DOCUMENT for stored chunks, RETRIEVAL_QUERY for the question. This single parameter visibly improves retrieval.
• Guard against hallucination in the prompt, not the pipelinepipelineAll active sales opportunities across the stages of the sales process, together with their combined potential value and probability of closing.Voir la définition complète →: instruct Gemini to answer only from the retrieved excerpts and to say when the answer is absent.